CN108305270A - A kind of storage grain worm number system and method based on mobile phone photograph - Google Patents
A kind of storage grain worm number system and method based on mobile phone photograph Download PDFInfo
- Publication number
- CN108305270A CN108305270A CN201810226464.2A CN201810226464A CN108305270A CN 108305270 A CN108305270 A CN 108305270A CN 201810226464 A CN201810226464 A CN 201810226464A CN 108305270 A CN108305270 A CN 108305270A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- grain worm
- connected domain
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 230000006866 deterioration Effects 0.000 claims abstract description 5
- 241001397056 Calamobius filum Species 0.000 abstract description 5
- 230000007423 decrease Effects 0.000 abstract description 3
- 238000012937 correction Methods 0.000 abstract description 2
- 241000607479 Yersinia pestis Species 0.000 description 6
- 241000238631 Hexapoda Species 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 230000035800 maturation Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
A kind of storage grain worm number system and method, the method based on mobile phone photograph in turn include the following steps：Step（1）：Obtain image；Step（2）：Coloured image gray processing is carried out to the image of acquisition and obtains gray level image；Step（3）：Gray level image is subjected to image slide window binary conversion treatment, the value of each pixel in image is assigned to " 0 " or " 255 "；Step（4）：To step（3）The image of acquisition carries out image deterioration；Step（5）：According to step（4）Obtained image carries out the counting of storage grain worm.Method of the present invention, compared with prior art, can improve brightness of image it is uneven cause statistical result accuracy rate decline the problem of, and using statistics with histogram choose grain worm distributed area method effectively increase grain borer population mesh statistical correction rate.
Description
Technical field
The invention belongs to grain borer population mesh counted fields more particularly to a kind of storage grain worm number systems based on mobile phone photograph
And method.
Background technology
During storing in a warehouse grain worm integrated control, grain storage insect pest quantity control to grain storage formed damage range with
It is interior, the heavy losses of grain storage both will not be excessively caused because of number of pest, it will not be unnecessary caused by excessively administering insect pest
Waste aggravates the pollution to grain and environment, so timely and accurately grasping storage insect pest information is particularly important.
Realize to the correct identification of grain storage insect pest and number statistical it is that storage grain worm is comprehensive in recent years using image processing techniques
It closes in prevention and has one of great-hearted crossing research direction.In recent years, there are some using image procossing to carry out early stage storage
The morphological character of the method that grain insect pest counts, main with good grounds grain worm object is counted, is based on grain worm Binary Sketch of Grey Scale Image
And the methods of the counting of pixel number analysis, it shows the feasibility of the storage grain worm information monitoring based on image procossing and has
Effect property, but these methods also have certain room for promotion in the accuracy when being counted to small grain worm, and exist
Image Acquisition and monitoring system hardware and software are expensive, and grain worm monitoring system cost is excessively high caused by when grain depot measuring point is more, with
And the problems such as cannot detecting in real time.
Invention content
The present invention is intended to provide a kind of easy to use, good storage grain worm number system based on mobile phone photograph of using effect
And method.
In order to solve the above technical problems, the present invention provides the following technical solutions：A kind of storage based on mobile phone photograph
Grain worm number system, the system comprises image capture modules and image processing module；
The image collected information is transferred to image processing module and handled by image capture module, and image processing module is to grain
Worm is identified and counts.
Described image acquisition module is camera.
The system also includes images to choose module, and the image collected information is transferred to image and selected by image capture module
Modulus block, image choose module and handle the image transmitting after selection to image processing module.
A kind of storage grain worm method of counting based on mobile phone photograph carried out using above system, the method include successively
Following steps：
Step（1）：Obtain image；
Step（2）：Coloured image gray processing is carried out to the image of acquisition and obtains gray level image；
Step（3）：Gray level image is subjected to image slide window binary conversion treatment, the value of each pixel in image is assigned to
" 0 " or " 255 "；
Step（4）：To step（3）The image of acquisition carries out image deterioration；
Step（5）：According to step（4）Obtained image carries out the counting of storage grain worm；
Method of counting is：
1）The connected domain in image is found, connected domain shares M；
2）The number for calculating pixel in each connected domain, by formula（2）Calculate each connection with same pixel point number
Ratio of the domain in total connected domain；
（Formula 2）
Wherein,M y To haveyThe total number of the connected domain of a pixel；W y To haveyThe connected domain of a pixel accounts for total company
The ratio in logical domain；
3）Using the number of pixel in connected domain as abscissa, the connected domain with same pixel point number is in total connected domain
Ratio be ordinate list histogram；
4）According to normal distribution, distributed area and 95.4% immediate section in histogram are calculated, using the section as grain worm
Connected domain value range；Connected domain outside the range is rejected；
5）According to the pixel number in each connected domain in immediate section, each pixel is 1 storage grain worm, finally
Find out the counting of storage grain worm.
In step（1）It needs to choose image range after obtaining image, by the image transmitting in selection range to step（2）Into
Row processing.
Step（3）By gray level image carry out image slide window binary conversion treatment specific method be：
（1）N number of base unit is divided an image into, the size of base unit is n × n pixel；
（2）Pixel in base unit is pressed into formula（1）Seek threshold value；
（i=1~n；j=1~n）（Formula 1）
Wherein,XFor gray threshold in a base unit；x ij It isiRowjThe gray value of the pixel of row；
（3）Again assignment is carried out to the gray value of each pixel in base unit；
Wherein,It is after assignment againiRowjThe gray value of the pixel of row.
Base unit is the square matrices of 3*3 pixel sizes.
Step（2）：Carrying out the method that coloured image gray processing obtains gray level image to the image of acquisition is：By cromogram
Each pixel of picture is converted into（0~255）Numerical value.
Step（2）Later, it needs to stretch gray level image, the method for stretching is：Note thepThe gray scale of a pixel
Change value isH p , according to formula（3）The pixel point value of image after being stretched：
（Formula 3）
Wherein,H p It ispThe gray processing value of a pixel；
For the pixel point value of p-th of pixel after image stretch；
For setting value.
In step（5）Method of counting in, the 1st）Walking the method for finding the connected domain in image is：By tool adjacent to each other
There is the pixel region of pixel value " 255 " to extract, i.e., since first pixel, finds the picture with pixel value " 255 "
Vegetarian refreshments, then whether inquire centered on the pixel its upper and lower, left and right, upper left, lower-left, upper right, the pixel of bottom right eight same
It for " 255 ", and is extrapolated with this, is removed until finding entire closed communicating domain, and by these points.
By above technical scheme, beneficial effects of the present invention are：The present invention proposes a kind of storehouse based on mobile phone photograph
Grain storage worm method of counting, compared with prior art, this method can improve that brightness of image is uneven to cause statistical result accuracy rate
The problem of decline, and the method for grain worm distributed area chosen using statistics with histogram to effectively increase grain worm number statistical correct
Rate.
Description of the drawings
Fig. 1 is schematic structural view of the invention；
Fig. 2 is original image samples 1；
Fig. 3 is original image samples 2；
Fig. 4 is original image samples 3；
Fig. 5 is the binary image handling result using ensemble average gray scale as threshold value to original image samples 1；
Fig. 6 is the binary image handling result using ensemble average gray scale as threshold value to original image samples 2；
Fig. 7 is the binary image handling result using ensemble average gray scale as threshold value to original image samples 3；
Fig. 8 is the processing result image using sliding window binarization method to original sample 1；
Fig. 9 is the processing result image using sliding window binarization method to original sample 2；
Figure 10 is the processing result image using sliding window binarization method to original sample 3.
Specific implementation mode
A kind of storage grain worm number system based on mobile phone photograph, as shown in Figure 1, the system comprises Image Acquisition moulds
Block, image choose module and image processing module；
The image collected information is transferred to image and chooses module by image capture module, and image chooses module by the figure after selection
It is handled as being transferred to image processing module, image processing module is identified and counts to grain worm.
Wherein, described image acquisition module is camera.
When in use, Image Acquisition is come by camera, the imagery exploitation image that acquisition is come chooses mould
Block selection range, wherein image chooses the prior art that module is ripe, has in existing cell-phone camera system extensive
Using such as existing mobile phone chooses the photo taken certain range, just chooses the function that module is realized for image.
The invention also discloses a kind of storage grain worm method of counting based on mobile phone photograph carried out using above system, institutes
The method of stating in turn includes the following steps：
Step（1）：Obtain image；Image is obtained specifically by camera.
In order to improve the accuracy of counting, in step（1）It needs to choose image range after obtaining image, it will be in selection range
Image transmitting to step（2）It is handled.Specifically, it is to choose what module was realized by image to choose image range, realization side
Method is the prior art of maturation.
Step（2）：Coloured image gray processing is carried out to the image of acquisition and obtains gray level image；
Specific method is：It converts each pixel of coloured image to（0~255）Numerical value, this is the ripe prior art.
In step（2）Later, it needs to stretch gray level image, the method for stretching is：Note thepThe ash of a pixel
Degreeization value isH p , according to formula（3）The pixel point value of image after being stretched：
（Formula 3）
Wherein,H p It ispThe gray processing value of a pixel；
For the pixel point value of p-th of pixel after image stretch；
For setting value, user can oneself selection.
Step（3）：Gray level image after stretching is subjected to image slide window binary conversion treatment, by each pixel in image
The value of point is assigned to " 0 " or " 255 ".
Wherein, it is by the specific method of gray level image progress image slide window binary conversion treatment：
（1）N number of base unit is divided an image into, the size of base unit is n × n pixel；It is substantially single in the present embodiment
Position is the square matrices of 3 × 3 pixel sizes.
（2）Pixel in base unit is pressed into formula（1）Seek threshold value；
（i=1~n；j=1~n）（Formula 1）
Wherein,XFor gray threshold in a base unit；x ij It isiRowjThe gray value of the pixel of row；
（3）Again assignment is carried out to the gray value of each pixel in base unit；
Wherein,It is after assignment againiRowjThe gray value of the pixel of row.
By selecting sliding window binary conversion treatment, avoid because there is process exposure deficiency of taking pictures, image brightness distribution
Non-uniform phenomenon causes intensity profile uneven, and then influences the selection of general image binary-state threshold, causes binaryzation
Image fault, to the identification of later stage grain worm and counting have a larger impact and there are the problem of, can preferably keep picture quality.
Step（4）：To step（3）The image of acquisition carries out image deterioration, wherein image deterioration is the existing skill of maturation
Art can be realized using existing method.
By degrading to image, image data amount is reduced, ensures the real-time of detection and identification.
Step（5）：According to step（4）Obtained image carries out the counting of storage grain worm；
Method of counting is：
1）The connected domain in image is found, connected domain shares M；Wherein, the method for the connected domain in searching image is：It will be mutual
The adjacent pixel region with pixel value " 255 " extracts, i.e., since first pixel, finding has pixel value
The pixel of " 255 ", then its upper and lower, left and right, upper left, lower-left, upper right, the pixel of bottom right eight are inquired centered on the pixel
Whether point is all " 255 ", and is extrapolated with this, is removed until finding entire closed communicating domain, and by these points, to prevent repeating
Technology.
2）The number for calculating pixel in each connected domain, by formula（2）It calculates each with same pixel point number
Ratio of the connected domain in total connected domain；
（Formula 2）
Wherein,M y To haveyThe total number of the connected domain of a pixel；W y To haveyThe connected domain of a pixel accounts for total company
The ratio in logical domain；
3）Using the number of pixel in connected domain as abscissa, the connected domain with same pixel point number is in total connected domain
Ratio be ordinate list histogram；
4）According to normal distribution, distributed area and 95.4% immediate section in histogram are calculated, using the section as grain worm
Connected domain value range；Connected domain outside the range is rejected；
5）According to the pixel number in each connected domain in immediate section, each pixel is 1 storage grain worm, finally
Find out the counting of storage grain worm.
As shown in table 1 below, each connected domain number of pixels of histogram of certain experiment levels off to normal distribution, we choose it
Distributed area and connected domain value range of immediate 95.4% numerical value of actual value as grain worm, and by the connected domain outside range
Ignore as distracter, then by pixel number be 18 ~ 24 connected domain 2 be used as immediate section, by connected domain 1 be connected to
It rejects in domain 3.The results show, this method reduce the noises such as the randomness of the lens focus of mobile phone photograph to count results standard
The influence of true property, effectively increases the accuracy of system grain worm number statistical.
The statistics with histogram situation of the connected domain of 1 certain experiment test of table
| It is connected to field type | Shared pixel number | Similar connected domain number（It is a） | Proportion（/ connected domain number） |
| Connected domain 1 | Less than 18 | 6 | 5.08% |
| Connected domain 2 | 18-24 | 110 | 94.23% |
| Connected domain 3 | More than 24 | 2 | 1.69% |
Effect analysis：
Select three original image samples comprising different brightness and density as shown in Fig. 2,3 and Fig. 4 herein.Using whole flat
Equal gray scale as threshold value binary image handling result respectively as shown in Fig. 5,6 and Fig. 7.Using sliding window two proposed in this paper
The processing result image of value method is respectively as shown in Fig. 8,9 and Figure 10.
It is found by the Comparative result of Fig. 2 ~ 10, after the image procossing of sliding window binarization method, the comparison of grain worm and background
It spends more obvious.Experimental result is consistent with theory analysis.
In terms of grain worm number statistical：Using Figure 10 as test sample, obtain the statistics with histogram method of this paper with it is traditional
The statistics accuracy rate comparing result of connected domain algorithm is as shown in table 2.
The grain worm number statistical accuracy rate of 3 distinct methods of table
| Statistical method | Grain borer population mesh（It is a） | Accuracy rate（Practical grain borer population mesh is 60） |
| The connected domain statistic law of fixed threshold values | 72 | 80% |
| Statistics with histogram method | 57 | 95% |
Statistics with histogram algorithm proposed in this paper it can be seen from the data result shown in table 3 effectively increases grain worm statistics
Accuracy rate.
The present invention proposes a kind of storage grain worm method of counting based on mobile phone photograph, compared with prior art, this method
Can improve brightness of image it is uneven cause statistical result accuracy rate decline the problem of, and using statistics with histogram choose grain worm
The method of distributed area effectively increases grain borer population mesh statistical correction rate.
Claims (10)
1. a kind of storage grain worm number system based on mobile phone photograph, it is characterised in that：The system comprises image capture modules
And image processing module；
The image collected information is transferred to image processing module and handled by image capture module, and image processing module is to grain
Worm is identified and counts.
2. the storage grain worm number system based on mobile phone photograph as described in claim 1, it is characterised in that：Described image acquires
Module is camera.
3. the storage grain worm number system based on mobile phone photograph as claimed in claim 2, it is characterised in that：The system is also wrapped
It includes image and chooses module, the image collected information is transferred to image and chooses module by image capture module, and image chooses module
Image transmitting after selection is handled to image processing module.
4. a kind of storage grain worm method of counting based on mobile phone photograph carried out using system described in claim 1, feature are existed
In：The method in turn includes the following steps：
Step（1）：Obtain image；
Step（2）：Coloured image gray processing is carried out to the image of acquisition and obtains gray level image；
Step（3）：Gray level image is subjected to image slide window binary conversion treatment, the value of each pixel in image is assigned to
" 0 " or " 255 "；
Step（4）：To step（3）The image of acquisition carries out image deterioration；
Step（5）：According to step（4）Obtained image carries out the counting of storage grain worm；
Method of counting is：
1）The connected domain in image is found, connected domain shares M；
2）The number for calculating pixel in each connected domain, by formula（2）Calculate each connection with same pixel point number
Ratio of the domain in total connected domain；
（Formula 2）
Wherein,M y To haveyThe total number of the connected domain of a pixel；W y To haveyThe connected domain of a pixel accounts for total connection
The ratio in domain；
3）Using the number of pixel in connected domain as abscissa, the connected domain with same pixel point number is in total connected domain
Ratio be ordinate list histogram；
4）According to normal distribution, distributed area and 95.4% immediate section in histogram are calculated, using the section as grain worm
Connected domain value range；Connected domain outside the range is rejected；
5）According to the pixel number in each connected domain in immediate section, each pixel is 1 storage grain worm, finally
Find out the counting of storage grain worm.
5. the storage grain worm method of counting based on mobile phone photograph as claimed in claim 4, it is characterised in that：In step（1）It obtains
It needs to choose image range after taking image, by the image transmitting in selection range to step（2）It is handled.
6. the storage grain worm method of counting based on mobile phone photograph as claimed in claim 4, it is characterised in that：Step（3）It will be grey
Degreeization image carry out image slide window binary conversion treatment specific method be：
（1）N number of base unit is divided an image into, the size of base unit is n × n pixel；
（2）Pixel in base unit is pressed into formula（1）Seek threshold value；
（i=1~n；j=1~n）（Formula 1）
Wherein,XFor gray threshold in a base unit；x ij It isiRowjThe gray value of the pixel of row；
（3）Again assignment is carried out to the gray value of each pixel in base unit；
Wherein,It is after assignment againiRowjThe gray value of the pixel of row.
7. the storage grain worm method of counting based on mobile phone photograph as claimed in claim 4, it is characterised in that：Base unit is 3*
The square matrices of 3 pixel sizes.
8. the storage grain worm method of counting based on mobile phone photograph as claimed in claim 4, it is characterised in that：Step（2）：To obtaining
The image taken carries out the method that coloured image gray processing obtains gray level image：It converts each pixel of coloured image to
（0~255）Numerical value.
9. the storage grain worm method of counting based on mobile phone photograph as claimed in claim 4, it is characterised in that：Step（2）Later,
It needs to stretch gray level image, the method for stretching is：Note thepThe gray processing value of a pixel isH p , according to formula（3）
The pixel point value of image after being stretched：
（Formula 3）
Wherein,H p It ispThe gray processing value of a pixel；
For the pixel point value of p-th of pixel after image stretch；
For setting value.
10. the storage grain worm method of counting based on mobile phone photograph as claimed in claim 4, it is characterised in that：In step（5）'s
In method of counting, the 1st）The method of connected domain found in step in image is：By the picture with pixel value " 255 " adjacent to each other
Plain extracted region comes out, i.e., since first pixel, finds the pixel with pixel value " 255 ", then with the pixel
Centered on inquire its upper and lower, left and right, whether upper left, lower-left, upper right, the pixel of bottom right eight are all " 255 ", and in addition
It pushes away, is removed until finding entire closed communicating domain, and by these points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810226464.2A CN108305270B (en) | 2018-03-19 | 2018-03-19 | Storage grain insect counting system and method based on mobile phone photographing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810226464.2A CN108305270B (en) | 2018-03-19 | 2018-03-19 | Storage grain insect counting system and method based on mobile phone photographing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108305270A true CN108305270A (en) | 2018-07-20 |
| CN108305270B CN108305270B (en) | 2022-11-01 |
Family
ID=62850297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810226464.2A Active CN108305270B (en) | 2018-03-19 | 2018-03-19 | Storage grain insect counting system and method based on mobile phone photographing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108305270B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272103A (en) * | 2018-08-01 | 2019-01-25 | 河南工业大学 | The method that a kind of pair of number of pest carries out express statistic |
| CN109872301A (en) * | 2018-12-26 | 2019-06-11 | 浙江清华长三角研究院 | A kind of color image preprocess method counted for rice pest identification |
| CN111507959A (en) * | 2020-04-15 | 2020-08-07 | 江苏科恒环境科技有限公司 | Mushroom head quantity statistical system based on image recognition |
| CN111639572A (en) * | 2020-05-22 | 2020-09-08 | 上海交通大学 | Method for estimating efficient flower volume of vine month season |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070291288A1 (en) * | 2006-06-15 | 2007-12-20 | Richard John Campbell | Methods and Systems for Segmenting a Digital Image into Regions |
| CN101170641A (en) * | 2007-12-05 | 2008-04-30 | 北京航空航天大学 | A method for image edge detection based on threshold sectioning |
| CN101976350A (en) * | 2010-10-20 | 2011-02-16 | 中国农业大学 | Grain storage pest detection and identification method based on video analytics and system thereof |
| CN103246872A (en) * | 2013-04-28 | 2013-08-14 | 北京农业智能装备技术研究中心 | Broad spectrum insect situation automatic forecasting method based on computer vision technology |
| CN104700417A (en) * | 2015-01-19 | 2015-06-10 | 湖南大学 | Computer image based automatic identification method of timber knot flaws |
| CN104796591A (en) * | 2015-05-04 | 2015-07-22 | 武向文 | Pest amount collecting and processing system and method |
| CN104866897A (en) * | 2015-06-12 | 2015-08-26 | 合肥市徽腾网络科技有限公司 | Aphid situation investigation method and device |
| CN105374015A (en) * | 2015-10-27 | 2016-03-02 | 湖北工业大学 | Binary method for low-quality document image based on local contract and estimation of stroke width |
| CN106447020A (en) * | 2016-09-13 | 2017-02-22 | 上海海事大学 | Intelligent bacterium colony counting method |
| CN106483129A (en) * | 2016-09-23 | 2017-03-08 | 电子科技大学 | A kind of method of the leukorrhea trichomonad automatic detection based on motion estimate |
| CN106815819A (en) * | 2017-01-24 | 2017-06-09 | 河南工业大学 | Many strategy grain worm visible detection methods |
| CN107545557A (en) * | 2016-06-23 | 2018-01-05 | 爱威科技股份有限公司 | Egg detecting method and device in excrement image |
| CN107644200A (en) * | 2017-08-30 | 2018-01-30 | 中国农业大学 | Pest and disease damage gradient of infection detection method and system based on Android system |
| CN107730470A (en) * | 2017-10-18 | 2018-02-23 | 四川理工学院 | A kind of multiple dimensioned improvement Retinex image enchancing methods blocked with histogram of explicit expression |
-
2018
- 2018-03-19 CN CN201810226464.2A patent/CN108305270B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070291288A1 (en) * | 2006-06-15 | 2007-12-20 | Richard John Campbell | Methods and Systems for Segmenting a Digital Image into Regions |
| CN101170641A (en) * | 2007-12-05 | 2008-04-30 | 北京航空航天大学 | A method for image edge detection based on threshold sectioning |
| CN101976350A (en) * | 2010-10-20 | 2011-02-16 | 中国农业大学 | Grain storage pest detection and identification method based on video analytics and system thereof |
| CN103246872A (en) * | 2013-04-28 | 2013-08-14 | 北京农业智能装备技术研究中心 | Broad spectrum insect situation automatic forecasting method based on computer vision technology |
| CN104700417A (en) * | 2015-01-19 | 2015-06-10 | 湖南大学 | Computer image based automatic identification method of timber knot flaws |
| CN104796591A (en) * | 2015-05-04 | 2015-07-22 | 武向文 | Pest amount collecting and processing system and method |
| CN104866897A (en) * | 2015-06-12 | 2015-08-26 | 合肥市徽腾网络科技有限公司 | Aphid situation investigation method and device |
| CN105374015A (en) * | 2015-10-27 | 2016-03-02 | 湖北工业大学 | Binary method for low-quality document image based on local contract and estimation of stroke width |
| CN107545557A (en) * | 2016-06-23 | 2018-01-05 | 爱威科技股份有限公司 | Egg detecting method and device in excrement image |
| CN106447020A (en) * | 2016-09-13 | 2017-02-22 | 上海海事大学 | Intelligent bacterium colony counting method |
| CN106483129A (en) * | 2016-09-23 | 2017-03-08 | 电子科技大学 | A kind of method of the leukorrhea trichomonad automatic detection based on motion estimate |
| CN106815819A (en) * | 2017-01-24 | 2017-06-09 | 河南工业大学 | Many strategy grain worm visible detection methods |
| CN107644200A (en) * | 2017-08-30 | 2018-01-30 | 中国农业大学 | Pest and disease damage gradient of infection detection method and system based on Android system |
| CN107730470A (en) * | 2017-10-18 | 2018-02-23 | 四川理工学院 | A kind of multiple dimensioned improvement Retinex image enchancing methods blocked with histogram of explicit expression |
Non-Patent Citations (6)
| Title |
|---|
| HUANG JING 等: "Research on the Rice Counting Method Based on Connected Component Labeling", 《2014 SIXTH INTERNATIONAL CONFERENCE ON MEASURING TECHNOLOGY AND MECHATRONICS AUTOMATION》 * |
| 刘忠强: "作物育种辅助决策关键技术研究与应用", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 张烨 等: "手背静脉图像二值化阈值算法", 《包装工程》 * |
| 张玉娟 等: "《遥感数字图像处理》", 31 July 2016 * |
| 朱亚娜 等: "仓储粮虫监测系统研究", 《中国农机化学报》 * |
| 马作炳 等: "《数学教学与模式创新》", 30 June 2017 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272103A (en) * | 2018-08-01 | 2019-01-25 | 河南工业大学 | The method that a kind of pair of number of pest carries out express statistic |
| CN109872301A (en) * | 2018-12-26 | 2019-06-11 | 浙江清华长三角研究院 | A kind of color image preprocess method counted for rice pest identification |
| CN109872301B (en) * | 2018-12-26 | 2022-07-15 | 浙江清华长三角研究院 | Color image preprocessing method for rice pest and disease identification and counting |
| CN111507959A (en) * | 2020-04-15 | 2020-08-07 | 江苏科恒环境科技有限公司 | Mushroom head quantity statistical system based on image recognition |
| CN111639572A (en) * | 2020-05-22 | 2020-09-08 | 上海交通大学 | Method for estimating efficient flower volume of vine month season |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108305270B (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108305270A (en) | A kind of storage grain worm number system and method based on mobile phone photograph | |
| CN108446617B (en) | Side face interference resistant rapid human face detection method | |
| CN106910186B (en) | Bridge crack detection and positioning method based on CNN deep learning | |
| CN109684922B (en) | Multi-model finished dish identification method based on convolutional neural network | |
| CN105046252B (en) | A kind of RMB prefix code recognition methods | |
| CN109859181A (en) | A kind of PCB welding point defect detection method | |
| CN101059425A (en) | Method and device for identifying different variety green tea based on multiple spectrum image texture analysis | |
| CN107038416B (en) | Pedestrian detection method based on binary image improved HOG characteristics | |
| CN107871316B (en) | Automatic X-ray film hand bone interest area extraction method based on deep neural network | |
| CN111062938B (en) | Plate expansion plug detection system and method based on machine learning | |
| CN109903282B (en) | Cell counting method, system, device and storage medium | |
| CN109242826B (en) | Mobile equipment end stick-shaped object root counting method and system based on target detection | |
| CN109145848B (en) | Wheat ear counting method | |
| CN111738114B (en) | Vehicle target detection method based on anchor-free accurate sampling remote sensing image | |
| CN109146859A (en) | A kind of pavement crack detection system based on machine vision | |
| CN111062293A (en) | Unmanned aerial vehicle forest flame identification method based on deep learning | |
| CN109859257A (en) | A kind of skin image texture appraisal procedure and system based on grain direction | |
| CN117274113B (en) | Broken silicon wafer cleaning effect visual detection method based on image enhancement | |
| CN108664839A (en) | A kind of image processing method and equipment | |
| CN115131359A (en) | Method for detecting pitting defects on surface of metal workpiece | |
| CN115131325A (en) | Breaker fault operation and maintenance monitoring method and system based on image recognition and analysis | |
| CN111311562B (en) | Ambiguity detection method and device for virtual focus image | |
| CN113313107A (en) | Intelligent detection and identification method for multiple types of diseases on cable surface of cable-stayed bridge | |
| CN110751667A (en) | Method for detecting infrared dim small target under complex background based on human visual system | |
| CN108734054B (en) | Non-shielding citrus fruit image identification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |